Frequency Decomposition to Tap the Potential of Single Domain for Generalization

TL;DR

This paper introduces a frequency decomposition method for single source domain generalization, dividing images into multiple frequency subdomains to enhance the learning of domain invariant features, outperforming existing methods.

Contribution

It proposes a novel frequency-based approach that extracts domain invariant features from a single source domain by learning across multiple frequency subdomains.

Findings

Frequency decomposition helps learn difficult features.

The method outperforms state-of-the-art single-source DG techniques.

Learning in multiple frequency domains improves generalization.

Abstract

Domain generalization (DG), aiming at models able to work on multiple unseen domains, is a must-have characteristic of general artificial intelligence. DG based on single source domain training data is more challenging due to the lack of comparable information to help identify domain invariant features. In this paper, it is determined that the domain invariant features could be contained in the single source domain training samples, then the task is to find proper ways to extract such domain invariant features from the single source domain samples. An assumption is made that the domain invariant features are closely related to the frequency. Then, a new method that learns through multiple frequency domains is proposed. The key idea is, dividing the frequency domain of each original image into multiple subdomains, and learning features in the subdomain by a designed two branches network. In this way, the model is enforced to learn features from more samples of the specifically limited spectrum, which increases the possibility of obtaining the domain invariant features that might have previously been defiladed by easily learned features. Extensive experimental investigation reveals that 1) frequency decomposition can help the model learn features that are difficult to learn. 2) the proposed method outperforms the state-of-the-art methods of single-source domain generalization.